/* Allocate a new page table page and hook it in via the given entry */
static int p2m_create_table(struct domain *d,
lpae_t *entry)
{
struct p2m_domain *p2m = &d->arch.p2m;
struct page_info *page;
void *p;
lpae_t pte;
BUG_ON(entry->p2m.valid);
page = alloc_domheap_page(NULL, 0);
if ( page == NULL )
return -ENOMEM;
page_list_add(page, &p2m->pages);
p = __map_domain_page(page);
clear_page(p);
unmap_domain_page(p);
pte = mfn_to_p2m_entry(page_to_mfn(page), MATTR_MEM);
write_pte(entry, pte);
return 0;
}
int p2m_alloc_table(struct domain *d)
{
struct p2m_domain *p2m = &d->arch.p2m;
struct page_info *page;
void *p;
/* First level P2M is 2 consecutive pages */
page = alloc_domheap_pages(NULL, 1, 0);
if ( page == NULL )
return -ENOMEM;
spin_lock(&p2m->lock);
page_list_add(page, &p2m->pages);
/* Clear both first level pages */
p = __map_domain_page(page);
clear_page(p);
unmap_domain_page(p);
p = __map_domain_page(page + 1);
clear_page(p);
unmap_domain_page(p);
p2m->first_level = page;
d->arch.vttbr = page_to_maddr(p2m->first_level)
| ((uint64_t)p2m->vmid&0xff)<<48;
spin_unlock(&p2m->lock);
return 0;
}
/*
* Allocate a new page table page and hook it in via the given entry.
* apply_one_level relies on this returning 0 on success
* and -ve on failure.
*
* If the existing entry is present then it must be a mapping and not
* a table and it will be shattered into the next level down.
*
* level_shift is the number of bits at the level we want to create.
*/
static int p2m_create_table(struct domain *d, lpae_t *entry,
int level_shift, bool_t flush_cache)
{
struct p2m_domain *p2m = &d->arch.p2m;
struct page_info *page;
lpae_t *p;
lpae_t pte;
int splitting = p2m_valid(*entry);
BUG_ON(p2m_table(*entry));
page = alloc_domheap_page(NULL, 0);
if ( page == NULL )
return -ENOMEM;
page_list_add(page, &p2m->pages);
p = __map_domain_page(page);
if ( splitting )
{
p2m_type_t t = entry->p2m.type;
unsigned long base_pfn = entry->p2m.base;
int i;
/*
* We are either splitting a first level 1G page into 512 second level
* 2M pages, or a second level 2M page into 512 third level 4K pages.
*/
for ( i=0 ; i < LPAE_ENTRIES; i++ )
{
pte = mfn_to_p2m_entry(base_pfn + (i<<(level_shift-LPAE_SHIFT)),
MATTR_MEM, t, p2m->default_access);
/*
* First and second level super pages set p2m.table = 0, but
* third level entries set table = 1.
*/
if ( level_shift - LPAE_SHIFT )
pte.p2m.table = 0;
write_pte(&p[i], pte);
}
}
else
clear_page(p);
if ( flush_cache )
clean_dcache_va_range(p, PAGE_SIZE);
unmap_domain_page(p);
pte = mfn_to_p2m_entry(page_to_mfn(page), MATTR_MEM, p2m_invalid,
p2m->default_access);
p2m_write_pte(entry, pte, flush_cache);
return 0;
}
int arch_iommu_populate_page_table(struct domain *d)
{
const struct domain_iommu *hd = dom_iommu(d);
struct page_info *page;
int rc = 0, n = 0;
d->need_iommu = -1;
this_cpu(iommu_dont_flush_iotlb) = 1;
spin_lock(&d->page_alloc_lock);
if ( unlikely(d->is_dying) )
rc = -ESRCH;
while ( !rc && (page = page_list_remove_head(&d->page_list)) )
{
if ( has_hvm_container_domain(d) ||
(page->u.inuse.type_info & PGT_type_mask) == PGT_writable_page )
{
unsigned long mfn = page_to_mfn(page);
unsigned long gfn = mfn_to_gmfn(d, mfn);
if ( gfn != gfn_x(INVALID_GFN) )
{
ASSERT(!(gfn >> DEFAULT_DOMAIN_ADDRESS_WIDTH));
BUG_ON(SHARED_M2P(gfn));
rc = hd->platform_ops->map_page(d, gfn, mfn,
IOMMUF_readable |
IOMMUF_writable);
}
if ( rc )
{
page_list_add(page, &d->page_list);
break;
}
}
static lpae_t mfn_to_p2m_entry(unsigned long mfn, unsigned int mattr,
p2m_type_t t)
{
paddr_t pa = ((paddr_t) mfn) << PAGE_SHIFT;
/* xn and write bit will be defined in the switch */
lpae_t e = (lpae_t) {
.p2m.af = 1,
.p2m.sh = LPAE_SH_OUTER,
.p2m.read = 1,
.p2m.mattr = mattr,
.p2m.table = 1,
.p2m.valid = 1,
.p2m.type = t,
};
BUILD_BUG_ON(p2m_max_real_type > (1 << 4));
switch (t)
{
case p2m_ram_rw:
e.p2m.xn = 0;
e.p2m.write = 1;
break;
case p2m_ram_ro:
e.p2m.xn = 0;
e.p2m.write = 0;
break;
case p2m_map_foreign:
case p2m_grant_map_rw:
case p2m_mmio_direct:
e.p2m.xn = 1;
e.p2m.write = 1;
break;
case p2m_grant_map_ro:
case p2m_invalid:
e.p2m.xn = 1;
e.p2m.write = 0;
break;
case p2m_max_real_type:
BUG();
break;
}
ASSERT(!(pa & ~PAGE_MASK));
ASSERT(!(pa & ~PADDR_MASK));
e.bits |= pa;
return e;
}
/* Allocate a new page table page and hook it in via the given entry */
static int p2m_create_table(struct domain *d,
lpae_t *entry)
{
struct p2m_domain *p2m = &d->arch.p2m;
struct page_info *page;
void *p;
lpae_t pte;
BUG_ON(entry->p2m.valid);
page = alloc_domheap_page(NULL, 0);
if ( page == NULL )
return -ENOMEM;
page_list_add(page, &p2m->pages);
p = __map_domain_page(page);
clear_page(p);
unmap_domain_page(p);
pte = mfn_to_p2m_entry(page_to_mfn(page), MATTR_MEM, p2m_invalid);
write_pte(entry, pte);
return 0;
}
enum p2m_operation {
INSERT,
ALLOCATE,
REMOVE,
RELINQUISH,
CACHEFLUSH,
};
static int apply_p2m_changes(struct domain *d,
enum p2m_operation op,
paddr_t start_gpaddr,
paddr_t end_gpaddr,
paddr_t maddr,
int mattr,
p2m_type_t t)
{
int rc;
struct p2m_domain *p2m = &d->arch.p2m;
lpae_t *first = NULL, *second = NULL, *third = NULL;
paddr_t addr;
unsigned long cur_first_page = ~0,
cur_first_offset = ~0,
cur_second_offset = ~0;
unsigned long count = 0;
unsigned int flush = 0;
bool_t populate = (op == INSERT || op == ALLOCATE);
lpae_t pte;
spin_lock(&p2m->lock);
if ( d != current->domain )
p2m_load_VTTBR(d);
addr = start_gpaddr;
while ( addr < end_gpaddr )
{
if ( cur_first_page != p2m_first_level_index(addr) )
{
if ( first ) unmap_domain_page(first);
first = p2m_map_first(p2m, addr);
if ( !first )
{
rc = -EINVAL;
goto out;
}
cur_first_page = p2m_first_level_index(addr);
}
if ( !first[first_table_offset(addr)].p2m.valid )
{
if ( !populate )
{
addr = (addr + FIRST_SIZE) & FIRST_MASK;
continue;
}
rc = p2m_create_table(d, &first[first_table_offset(addr)]);
if ( rc < 0 )
{
printk("p2m_populate_ram: L1 failed\n");
goto out;
}
}
BUG_ON(!first[first_table_offset(addr)].p2m.valid);
if ( cur_first_offset != first_table_offset(addr) )
{
if (second) unmap_domain_page(second);
second = map_domain_page(first[first_table_offset(addr)].p2m.base);
cur_first_offset = first_table_offset(addr);
}
/* else: second already valid */
if ( !second[second_table_offset(addr)].p2m.valid )
{
if ( !populate )
{
addr = (addr + SECOND_SIZE) & SECOND_MASK;
continue;
}
rc = p2m_create_table(d, &second[second_table_offset(addr)]);
if ( rc < 0 ) {
printk("p2m_populate_ram: L2 failed\n");
goto out;
}
}
BUG_ON(!second[second_table_offset(addr)].p2m.valid);
if ( cur_second_offset != second_table_offset(addr) )
{
/* map third level */
if (third) unmap_domain_page(third);
third = map_domain_page(second[second_table_offset(addr)].p2m.base);
cur_second_offset = second_table_offset(addr);
}
pte = third[third_table_offset(addr)];
flush |= pte.p2m.valid;
/* TODO: Handle other p2m type
*
* It's safe to do the put_page here because page_alloc will
* flush the TLBs if the page is reallocated before the end of
* this loop.
*/
if ( pte.p2m.valid && p2m_is_foreign(pte.p2m.type) )
{
unsigned long mfn = pte.p2m.base;
ASSERT(mfn_valid(mfn));
put_page(mfn_to_page(mfn));
}
/* Allocate a new RAM page and attach */
switch (op) {
case ALLOCATE:
{
struct page_info *page;
ASSERT(!pte.p2m.valid);
rc = -ENOMEM;
page = alloc_domheap_page(d, 0);
if ( page == NULL ) {
printk("p2m_populate_ram: failed to allocate page\n");
goto out;
}
pte = mfn_to_p2m_entry(page_to_mfn(page), mattr, t);
write_pte(&third[third_table_offset(addr)], pte);
}
break;
case INSERT:
{
pte = mfn_to_p2m_entry(maddr >> PAGE_SHIFT, mattr, t);
write_pte(&third[third_table_offset(addr)], pte);
maddr += PAGE_SIZE;
}
break;
case RELINQUISH:
case REMOVE:
{
if ( !pte.p2m.valid )
{
count++;
break;
}
count += 0x10;
memset(&pte, 0x00, sizeof(pte));
write_pte(&third[third_table_offset(addr)], pte);
count++;
}
break;
case CACHEFLUSH:
{
if ( !pte.p2m.valid || !p2m_is_ram(pte.p2m.type) )
break;
flush_page_to_ram(pte.p2m.base);
}
break;
}
/* Preempt every 2MiB (mapped) or 32 MiB (unmapped) - arbitrary */
if ( op == RELINQUISH && count >= 0x2000 )
{
if ( hypercall_preempt_check() )
{
p2m->lowest_mapped_gfn = addr >> PAGE_SHIFT;
rc = -EAGAIN;
goto out;
}
count = 0;
}
/* Got the next page */
addr += PAGE_SIZE;
}
if ( flush )
{
/* At the beginning of the function, Xen is updating VTTBR
* with the domain where the mappings are created. In this
* case it's only necessary to flush TLBs on every CPUs with
* the current VMID (our domain).
*/
flush_tlb();
}
if ( op == ALLOCATE || op == INSERT )
{
unsigned long sgfn = paddr_to_pfn(start_gpaddr);
unsigned long egfn = paddr_to_pfn(end_gpaddr);
p2m->max_mapped_gfn = MAX(p2m->max_mapped_gfn, egfn);
p2m->lowest_mapped_gfn = MIN(p2m->lowest_mapped_gfn, sgfn);
}
rc = 0;
out:
if (third) unmap_domain_page(third);
if (second) unmap_domain_page(second);
if (first) unmap_domain_page(first);
if ( d != current->domain )
p2m_load_VTTBR(current->domain);
spin_unlock(&p2m->lock);
return rc;
}
